Developing a function to analyse rows of a data.table in R - r

Question

For a sample dataframe:
df1 <- structure(list(area = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("a",
"b"), class = "factor"), region = structure(c(1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), .Label = c("a1",
"a2", "b1", "b2"), class = "factor"), weight = c(0, 1.2, 3.2,
2, 1.6, 5, 1, 0.5, 0.2, 0, 1.5, 2.3, 1.5, 1.8, 1.6, 2, 1.3, 1.4,
1.5, 1.6, 2, 3, 4, 2.3, 1.3, 2.1, 1.3, 1.6, 1.7, 1.8, 2, 1.3,
1, 0.5), var.1 = c(0L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 1L, 0L, 1L,
1L, 0L, 1L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 0L, 1L,
0L, 0L, 0L, 1L, 0L, 1L, 0L), var.2 = c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 0L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 1L, 0L, 1L, 0L,
1L, 0L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L)), .Names = c("area",
"region", "weight", "var.1", "var.2"), class = c("data.table",
"data.frame"))
I want to first produce a summary table...
area_summary <- setDT(df1)[,.(.N, freq.1 = sum(var.1==1), result = weighted.mean((var.1==1),
w = weight)*100), by = area]
...and then populate it by running the following code for each area (e.g. a, b). This looks for the highest and lowest 'result' in each region, and then produces a xtabs and calculates the relative difference (RD) before adding these to the summary table. Here I have developed the code for area 'a':
#Include only regions with highest or lowest percentage
a_cntry <- subset(df1, area=="a")
a_cntry.summary <- setDT(a_cntry)[,.(.N, freq.1 = sum(var.1==1), result = weighted.mean((var.1==1),
w = weight)*100), by = region]
#Include only regions with highest or lowest percentage
incl <- a_cntry.summary[c(which.min(result), which.max(result)),region]
region <- as.data.frame.matrix(a_cntry)
a_cntry <- a_cntry[a_cntry$region %in% incl,]
#Produce xtabs table of RD
a_cntry.var.1 <- xtabs(weight ~ var.1 + region, data=a_cntry)
a_cntry.var.1
#Produce xtabs table
RD.var.1 <- prop.test(x=a_cntry.var.1[,2], n=rowSums(a_cntry.var.1), correct = FALSE)
RD <- round(- diff(RD.var.1$estimate), 3)
RDpvalue <- round(RD.var.1$"p.value", 4)
RD
RDpvalue
#Add RD and RDpvalue tosummary table
area_summary$RD[area_summary$area == "a"] <- RD
area_summary$RDpvalue[area_summary$area == "a"] <- RDpvalue
rm(RD, RD.var.1, RDpvalue, a_cntry.var.1, incl, a_cntry,a_cntry.summary,region)
I wish to wrap this code into a function, so I can just specify the 'areas' (in the 'area' column in df1) and then the code completes all the analysis and adds the results to the summary table.
If I wanted to call my function stats, I understand it may start like this:
stats= function (df1, x) {
apply(x)
}
If anyone can start me off developing my function, I should be most grateful.